MCRapper: Monte-Carlo Rademacher Averages for Poset Families and Approximate Pattern Mining
MCRapper: Monte-Carlo Rademacher Averages for Poset Families and Approximate Pattern Mining
复制标题
MCRapper:Poset 族的 Monte-Carlo Rademacher 平均值和近似模式挖掘
DOI:
10.1145/3532187
复制
发表时间:
2022
影响因子:
3.6
通讯作者:
Riondato, Matteo
中科院分区:
文献类型:
--
作者:
Pellegrina, Leonardo;Cousins, Cyrus;Vandin, Fabio;Riondato, Matteo
“I’m an MC still as honest” – Eminem, Rap GodWe presentMCRapper, an algorithm for efficient computation of Monte-Carlo Empirical Rademacher Averages (MCERA) for families of functions exhibiting poset (e.g., lattice) structure, such as those that arise in many pattern mining tasks. The MCERA allows us to compute upper bounds to the maximum deviation of sample means from their expectations, thus it can be used to find both(1)statistically-significant functions (i.e., patterns) when the available data is seen as a sample from an unknown distribution, and(2)approximations of collections of high-expectation functions (e.g., frequent patterns) when the available data is a small sample from a large dataset. This flexibility offered byMCRapperis a big advantage over previously proposed solutions, which could only achieve one of the two.MCRapperuses upper bounds to the discrepancy of the functions to efficiently explore and prune the search space, a technique borrowed from pattern mining itself. To show the practical use ofMCRapper, we employ it to develop an algorithmTFP-Rfor the task of True Frequent Pattern (TFP) mining, by appropriately computing approximations of the negative and positive borders of the collection of patterns of interest, which allow an effective pruning of the pattern space and the computation of strong bounds to the supremum deviation.TFP-Rgives guarantees on the probability of including any false positives (precision) and exhibits higher statistical power (recall) than existing methods offering the same guarantees. We evaluateMCRapperandTFP-Rand show that they outperform the state-of-the-art for their respective tasks.
登录
查看更多内容
DOI:
10.1145/2020408.2020500
发表时间:
2011-08
期刊:
--
影响因子:
--
作者:
Mario Boley;C. Lucchese;Daniel Paurat;Thomas Gärtner
通讯作者:
Mario Boley;C. Lucchese;Daniel Paurat;Thomas Gärtner
DOI:
10.1137/1.9781611974010.5
发表时间:
2014-07
期刊:
Informação & Informação
影响因子:
--
作者:
M. Sugiyama;F. Llinares-López;Niklas Kasenburg;Karsten M. Borgwardt
通讯作者:
M. Sugiyama;F. Llinares-López;Niklas Kasenburg;Karsten M. Borgwardt
DOI:
--
发表时间:
2022
期刊:
影响因子:
--
作者:
間宮悠;栃木透
通讯作者:
栃木透
DOI:
--
发表时间:
--
期刊:
影响因子:
--
作者:
通讯作者:
--
影响因子:
2.3
作者:
Diego Santoro;Andrea Tonon;Fabio Vandin
通讯作者:
Fabio Vandin